© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 6258
    Prev
    Next
    INDEX
    Explanations

    -

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     бро
    -0.08
    ไฟ
    -0.08
    _file
    -0.08
    .self
    -0.07
     влас
    -0.07
    หาร
    -0.07
    idão
    -0.07
    idenza
    -0.07
    рам
    -0.07
     αριθ
    -0.07
    POSITIVE LOGITS
     siglo
    0.26
     القرن
    0.26
     século
    0.25
     XIX
    0.19
    20
    0.19
     abad
    0.19
     twentieth
    0.18
    19
    0.18
     century
    0.18
     ХХ
    0.18
    Activations Density 0.031%

    No Known Activations